A method for automatically monitoring marine safety using buoys

Abstract

The present invention provides a method for automatically monitoring the safety of buoys at sea, which belongs to the technical field of monitoring methods. The method comprises the following steps: receiving buoy message data, the buoy message data including buoy latitude and longitude data, buoy voltage data, buoy anchor light data, buoy hatch data, buoy cabin water inflow data, and buoy sensor data; performing a multivariate decomposition operation on the buoy latitude and longitude data, and establishing a shift relationship function between the buoy displacement change component and the ambient wind speed change component; constructing a buoy shift matrix based on the shift relationship function, calculating the buoy public safety value, the buoy's own safety value, and the buoy's functional safety value, and performing a weighted calculation on the buoy public safety value, the buoy's own safety value, and the buoy's functional safety value to obtain a buoy safety assessment value; and determining the buoy risk level according to the buoy safety assessment value. The present invention solves the problem of how to accurately identify and assess the safety status of buoys at sea.

Description

Technical Field

[0001] The present invention belongs to the technical field of monitoring methods, and in particular relates to a method for automatically monitoring buoy maritime safety. Background Art

[0002] Ocean buoys are a vital component of the ocean observation network, undertaking multiple tasks, including marine environmental monitoring, channel marking, and marine scientific research. With the increase in marine development activities, buoys face increasing security threats, including risks of dragging anchors, collisions, and vandalism. Traditional buoy safety monitoring relies primarily on regular patrol inspections and single-parameter threshold monitoring, which suffers from large blind spots, delayed response, and high false alarm rates. Currently, three main technical approaches are used for buoy safety monitoring: the first is satellite-based position monitoring, which determines the safety status of the buoy by determining whether it has deviated from its predetermined position. However, this method struggles to distinguish between displacement caused by natural factors and vandalism, and positioning accuracy significantly decreases in adverse weather conditions. The second is sensor-based condition monitoring, which primarily monitors the operating status of key components such as the buoy's power supply, anchor lights, and hatches. However, each sensor operates independently, lacking systematic analysis and prone to misjudgment. The third is remote monitoring based on image recognition, which monitors the buoy via shore-based radar or video systems. However, weather, visibility, and monitoring range limitations make it difficult to achieve round-the-clock monitoring. In practical applications, these technical approaches often operate independently and lack effective data fusion and comprehensive analysis mechanisms. For example, a buoy monitoring system in a certain marine area often generates false alarms when using satellite positioning monitoring, as it cannot distinguish the cause of buoy displacement, resulting in unnecessary patrol inspections. Sensor monitoring, lacking environmental data support, makes it difficult to determine whether abnormal conditions are caused by inclement weather. And remote monitoring severely degrades monitoring effectiveness at night or in conditions of poor visibility. These issues lead to inefficient buoy safety management, increased operation and maintenance costs, and impact the stable operation of the ocean observation system. Summary of the Invention

[0003] In view of this, the present invention provides a method for automatically monitoring the safety of buoys at sea, which solves the problem of how to accurately identify and evaluate the safety status of buoys at sea.

[0004] The present invention is achieved in that:

[0005] The present invention provides a method for automatic monitoring of buoy maritime safety, which includes the following steps: receiving buoy message data, the buoy message data including buoy latitude and longitude data, buoy voltage data, buoy anchor light data, buoy cabin door data, buoy cabin water inflow data, and buoy sensor data; performing multivariate decomposition operation on the buoy latitude and longitude data, and establishing a shift relationship function between the buoy displacement change component and the ambient wind speed change component; constructing a buoy shift matrix based on the shift relationship function, calculating the buoy public safety value, the buoy's own safety value, and the buoy's functional safety value, and performing weighted calculation on the buoy public safety value, the buoy's own safety value, and the buoy's functional safety value to obtain a buoy safety assessment value; and determining the buoy risk level according to the buoy safety assessment value.

[0006] On the basis of the above technical solution, the method for automatic monitoring of maritime safety by buoys of the present invention can be further improved as follows:

[0007] Among them, the step of processing the buoy message data is specifically to receive the original message data through the communication receiving module, and use the recursive descent algorithm to process the hierarchical data structure, including message header parsing, data segment extraction, checksum verification, and use the state machine design pattern to handle data packet loss and disorder. The signal strength threshold is set to 25 decibels and the signal-to-noise ratio threshold is set to 10 decibels.

[0008] Furthermore, a multivariate decomposition operation is performed on the buoy longitude and latitude data, specifically converting the buoy longitude and latitude data into a time series, removing abnormal points using a median filtering method, and smoothing using a cubic spline interpolation method. The time series is decomposed into multiple intrinsic mode functions through an iterative screening process, and the iteration stop condition is set to a standard deviation threshold of 0.2 to obtain the buoy displacement stability component and the buoy displacement change component.

[0009] Furthermore, the step of establishing the displacement relationship function is to use the least squares method to establish the preliminary relationship between the buoy displacement change component and the ambient wind speed change component, construct the flow direction influence function through polynomial fitting, and use the genetic algorithm to optimize the model parameters. The population size is set to 100, the evolutionary generation is 50 generations, the crossover probability is 0.8, and the mutation probability is 0.1.

[0010] Furthermore, the step of constructing the buoy shift matrix is ​​to calculate the shift coefficient by the sliding window method, with the window length set to 6 hours and the sliding step length to 1 hour, calculate the displacement components in three orthogonal directions, use the maximum and minimum method for normalization, calculate the eigenvalue by the power iteration method, and set the convergence threshold to 0.001.

[0011] Furthermore, the step of calculating the public safety value of the buoy is to use the eigenvalue decomposition method to extract the main movement direction of the buoy displacement matrix, combine the buoy stability matrix to evaluate the displacement stability, and use the fuzzy comprehensive evaluation method to evaluate the potential impact of the buoy on public safety.

[0012] Furthermore, the step of calculating the buoy's own safety value specifically includes using a trend analysis method to evaluate the buoy voltage change trend, using a spectrum analysis method to identify abnormal cycles of the buoy anchor light matching function, and evaluating the buoy hatch data and buoy cabin water inflow data based on a decision tree method.

[0013] Furthermore, the step of calculating the functional safety value of the buoy is to use a data quality control method to identify abnormal values ​​and missing values ​​of the buoy sensor data, calculate the time continuity index and spatial consistency index of the data, and use the hierarchical analysis method to determine the index weights.

[0014] Furthermore, the calculation steps of the buoy safety assessment value are as follows: using the Delphi method to determine the initial weights of various safety indicators, optimizing the weight coefficients through the hierarchical analysis method and performing consistency tests, and using weighted summation to obtain the final buoy safety assessment value.

[0015] Furthermore, the step of determining the risk level of the buoy specifically adopts a cluster analysis method to determine the level boundary value, and adopts fuzzy rule reasoning to judge the risk level of the buoy.

[0016] Compared to existing technologies, the present invention provides a method for automatically monitoring buoy safety at sea, demonstrating the following benefits: By establishing a buoy safety monitoring model that integrates multi-source data, the present invention achieves accurate identification and assessment of the buoy's safety status. First, empirical mode decomposition (EMD) is used to perform multi-scale analysis on buoy displacement data, effectively separating displacement characteristics caused by natural and human factors, thereby improving the accuracy of abnormal state identification. Second, a displacement relationship function is constructed to quantitatively correlate buoy displacement with environmental factors, enabling the system to accurately determine whether the displacement is normal. Third, time-frequency analysis is used to process status data such as voltage and anchor lights, combining it with environmental data for a comprehensive assessment, reducing the false alarm rate. Finally, a safety assessment system based on multi-index weighting is established, enabling quantitative assessment of safety status. The present invention overcomes the limitations of traditional monitoring methods and establishes a comprehensive buoy safety monitoring technology system. This solution not only accurately identifies abnormal buoy states but also predicts potential safety risks, providing a scientific basis for buoy safety management. The system is highly adaptable and can automatically adjust parameters based on the environmental characteristics of different sea areas, making it highly applicable. Through a multi-level data analysis and evaluation mechanism, comprehensive monitoring of the safety status of buoys is achieved, providing strong guarantees for the stable operation of the ocean observation network. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The figure is a flow chart of a method for automatic monitoring of buoy marine safety. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0019] like Figure 1 FIG. 1 is a flow chart of a method for automatically monitoring marine safety of a buoy provided by the present invention. The method comprises the following steps:

[0020] S01, receiving buoy message data, wherein the buoy message data includes buoy latitude and longitude data, buoy voltage data, buoy anchor light data, buoy hatch data, buoy cabin water inflow data, and buoy sensor data;

[0021] The specific implementation of step S01 involves using a communication receiving module to acquire buoy message data, which involves a data parsing process. First, the raw message data is received via the satellite communication module. This message data contains various sensor data and a communication protocol header, requiring protocol parsing. After protocol parsing, buoy latitude and longitude data, buoy voltage data, buoy anchor light data, buoy hatch data, buoy cabin water inflow data, and buoy sensor data are obtained. The communication protocol utilizes the universal ocean monitoring data format specification, and data parsing employs a recursive descent algorithm to process hierarchical data structures. The parsing process includes three stages: message header parsing, data segment extraction, and checksum verification. The data parsing module utilizes a state machine design pattern, effectively handling packet loss and out-of-order processing. Regarding data reception quality, the signal strength threshold is set at 25 decibels, and the signal-to-noise ratio threshold is set at 10 decibels. Packets below the threshold are marked as pending confirmation. The purpose of this step is to ensure the integrity and accuracy of data reception, providing a reliable data foundation for subsequent analysis.

[0022] S02, performing a multivariate decomposition operation on the buoy latitude and longitude data to obtain a buoy displacement stability component and a buoy displacement variation component;

[0023] The specific implementation method of step S02 is to process the buoy longitude and latitude data based on the principle of empirical mode decomposition. First, the longitude and latitude data are converted into a time series, and the time series data is preprocessed, including outlier processing and data smoothing. The median filtering method is used to remove outliers in the data preprocessing, and the filter window size is set to 5 data points. The data is then smoothed using the cubic spline interpolation method, and the interpolation node interval is set to 30 minutes. The preprocessed data is then subjected to empirical mode decomposition, and the time series is decomposed into multiple intrinsic mode functions through an iterative screening process. During the decomposition process, the iteration stop condition is set to a standard deviation threshold of 0.2, and the maximum number of iterations is 10 times. Finally, the obtained intrinsic mode functions are divided into two categories: stable components of buoy displacement and variable components of buoy displacement. Among them, the components with a frequency lower than 0.1 Hz are classified as stable components, and the components higher than this frequency are classified as variable components. The purpose of this step is to separate the stable trend and fluctuation characteristics of the buoy displacement, providing a basis for subsequent displacement state judgment.

[0024] S03, obtaining environmental monitoring data, the environmental monitoring data including environmental wind speed data, environmental wind direction data, and environmental flow direction data, performing a multivariate decomposition operation on the environmental wind speed data to obtain an environmental wind speed stable component and an environmental wind speed variable component;

[0025] The specific implementation method of step S03 is to obtain and process environmental monitoring data. First, environmental wind speed data, environmental wind direction data and environmental flow direction data are obtained from the meteorological station, and the data sampling interval is 10 minutes. The obtained environmental data are subjected to quality control, including data range check and time continuity check. The effective range of wind speed data is set to 0 to 60 meters per second, and the range of wind direction data is 0 to 360 degrees. Data out of the range is corrected by interpolation method. Then the environmental wind speed data is subjected to multi-scale analysis by wavelet decomposition method, Debao wavelet is selected as the basis function, and the number of decomposition layers is set to 4 layers. The environmental wind speed stable component and the environmental wind speed variable component are obtained by reconstruction. The reconstruction process adopts the threshold denoising method, and the parameter of the soft threshold function is set to 3 times the standard deviation. The purpose of this step is to obtain high-quality environmental data and extract the main features of wind speed by signal processing method.

[0026] S04, establishing a displacement relationship function between the buoy displacement variation component and the ambient wind speed variation component, and constructing a buoy displacement matrix according to the displacement relationship function;

[0027] The specific implementation method of step S04 is to establish a correlation model between buoy displacement and environmental factors. First, the least squares method is used to establish a preliminary relationship between the buoy displacement change component and the environmental wind speed change component. A weighted strategy is adopted in the fitting process, and the weight of the recent data is set to a larger value. Then, the environmental flow direction data is introduced to construct a flow direction influence function. The function is obtained by polynomial fitting, and the polynomial order is set to 3. After that, a genetic algorithm is used to optimize the model parameters. The population size is set to 100, the evolutionary generations are 50 generations, the crossover probability is 0.8, and the mutation probability is 0.1. Finally, a displacement relationship function is obtained, which includes the comprehensive influence of environmental factors such as wind speed and flow direction. The purpose of this step is to construct an accurate buoy displacement prediction model to achieve accurate judgment of the buoy displacement status.

[0028] S05. Calculating a buoy stability matrix based on the buoy displacement matrix, and determining a buoy displacement state according to the buoy stability matrix;

[0029] The specific implementation method of step S05 is to calculate the buoy stability matrix based on the buoy displacement matrix and determine the displacement state. First, the displacement coefficient is calculated by the sliding window method, the window length is set to 6 hours, and the sliding step is 1 hour. For each time window, the displacement components in the three orthogonal directions are calculated, and the weighted average method is used to obtain the displacement coefficient. Then, a buoy stability matrix is ​​established, and the matrix elements are obtained by normalization processing, and the normalization process adopts the maximum and minimum method. Finally, the buoy displacement state is determined based on the eigenvalue of the stability matrix. The eigenvalue calculation adopts the power iteration method, and the convergence threshold is set to 0.001. The purpose of this step is to achieve quantitative judgment of the buoy displacement state through matrix analysis method.

[0030] S06, calculating a two-dimensional transformation value of the buoy voltage data, and determining a buoy voltage state according to the two-dimensional transformation value, which is recorded as a first buoy voltage determination result;

[0031] The specific implementation method of step S06 is to perform time-frequency analysis on the buoy voltage data. First, the voltage data is reconstructed into a time series using the delayed coordinate method. The delay time is determined using the mutual information method, and the embedding dimension is determined using the false nearest neighbor method. The reconstructed phase space is then projected two-dimensionally using principal component analysis. The spectral characteristics of the projected data are then calculated using the fast Fourier transform algorithm, with the number of transformation points set to 1024. The voltage state is determined based on the spectral characteristics, and the judgment criteria include the amplitude and frequency distribution characteristics of the main frequency component. The purpose of this step is to achieve early identification of abnormal buoy voltage conditions through time-frequency analysis methods.

[0032] S07: If the first determination result of the buoy voltage is abnormal, calculating a lateral value and a longitudinal value of the buoy voltage, and calculating a buoy voltage fluctuation value based on the lateral value and the longitudinal value of the buoy voltage;

[0033] The specific implementation of step S07 involves calculating quantitative indicators of the voltage status. First, the rate of change of the voltage data in the time and amplitude dimensions is calculated using a central difference method, with the difference step set to the sampling period. The spatial distribution characteristics of the rate of change are then calculated, including statistics such as mean, variance, and skewness. These characteristics are then combined to form a voltage fluctuation value. This combination process uses a weighted summation method, with the weight coefficients determined through principal component analysis. The purpose of this step is to establish a quantitative assessment indicator for the voltage status and provide an objective basis for abnormality judgment.

[0034] S08. Calculate the lateral variation value and the longitudinal variation value of the buoy anchor light data, establish a buoy anchor light matching function, and determine the seasonal conformity of the buoy anchor light data according to the buoy anchor light matching function;

[0035] The specific implementation of step S08 involves analyzing the temporal characteristics of the buoy anchor light data. First, theoretical sunrise and sunset times are calculated using an astronomical algorithm, which accounts for the influence of geographic location and seasonal variations. A theoretical model of the anchor light operating cycle is then constructed, using trigonometric functions to describe diurnal variations. The function parameters are obtained by fitting historical data using the least squares method. The degree of match between the actual anchor light status and the theoretical model is then calculated using correlation analysis. The purpose of this step is to determine whether the buoy anchor light system is functioning properly through analysis of the anchor light operating status.

[0036] S09, establishing a safety determination function based on the buoy hatch data and the buoy cabin water inflow data, and continuously monitoring for 3 hours to determine the buoy intrusion status according to the safety determination function;

[0037] The specific implementation of step S09 involves monitoring the status of the buoy's hatch and tank flooding. First, hatch and tank flooding data are digitized, and a threshold judgment method is used to convert the analog signals into discrete states. A state transition model is then constructed based on Markov chain theory, and state transition probabilities are estimated using statistical learning methods. The state assessment results are then updated in real time using a sliding time window with a window length of 3 hours. The purpose of this step is to achieve timely detection and alarm of buoy intrusion events.

[0038] S10, calculating the buoy public safety value according to the buoy displacement matrix and the buoy stability matrix;

[0039] The specific implementation of step S10 involves calculating the buoy's public safety value. First, the displacement trend is calculated based on the buoy's displacement matrix, and the main movement direction is extracted using eigenvalue decomposition. The stability of the displacement is then evaluated using the buoy's stability matrix, using a fuzzy comprehensive evaluation method. The public safety value is then calculated based on the evaluation results, taking into account factors such as distance from sensitive areas and movement speed. The purpose of this step is to quantify the potential impact of the buoy on public safety.

[0040] S11, calculating the buoy's own safety value based on the buoy voltage fluctuation value, the buoy anchor light matching function, and the safety determination function;

[0041] The specific implementation of step S11 involves calculating the buoy's inherent safety value. First, the time series characteristics of voltage fluctuations are analyzed, and trend analysis methods are used to assess voltage trends. Next, the periodic characteristics of the anchor light matching function are evaluated, and spectral analysis methods are used to identify abnormal periods. Finally, based on the output of the safety judgment function, a decision tree approach is used to comprehensively assess the buoy's inherent safety status. This step aims to evaluate the operating status of each of the buoy's subsystems and determine the buoy's inherent safety level.

[0042] S12, calculating a buoy functional safety value based on the lateral change value and the longitudinal change value of the buoy sensor data;

[0043] The specific implementation of step S12 involves calculating the functional safety value of the buoy. First, the buoy sensor data is quality assessed, using data quality control methods to identify outliers and missing values. The data's temporal continuity and spatial consistency indices are then calculated using statistical tests. The functional safety value is then derived by integrating multiple indicators. The analytic hierarchy process is used to determine indicator weights during this integration process. The purpose of this step is to assess the reliability of the buoy's observation function.

[0044] S13, performing weighted calculation on the buoy public safety value, the buoy's own safety value, and the buoy's functional safety value to obtain a buoy safety assessment value;

[0045] The specific implementation of step S13 involves calculating the buoy's safety assessment value. Initial weights for each safety indicator are first determined using an expert scoring method, employing the Delphi method. The weight coefficients are then optimized using the Analytic Hierarchy Process (AHP), a judgment matrix is ​​constructed, and a consistency check is performed. The weighted sum of each safety value is then calculated to yield the final safety assessment value. The purpose of this step is to quantify the overall safety status of the buoy.

[0046] S14, determining a buoy risk level according to the buoy safety assessment value;

[0047] The specific implementation of step S14 involves determining the buoy's risk level. First, risk classification criteria are established, and cluster analysis is used to determine the level boundaries. The buoy's risk level is then determined based on the safety assessment value, using fuzzy rule reasoning. Subsequently, appropriate action recommendations are automatically generated based on the risk level. The purpose of this step is to provide decision support for buoy safety management.

[0048] The specific implementation of the above steps is described in detail below:

[0049] The specific implementation of step S01 is to use the communication receiving module to obtain the buoy message data. First, the original message data is received through the satellite communication module. The message data at this time includes the buoy latitude and longitude data, buoy voltage data, buoy anchor light data, buoy hatch data, buoy cabin water inflow data, and buoy sensor data. During the data reception process, the signal quality index is used to Conduct quality assessment, including is the signal strength, is the noise intensity, is the signal amplitude, when When the noise level is lower than 25 decibels, the data retransmission mechanism needs to be triggered. The data parsing process uses a recursive descent algorithm to process the hierarchical data structure, including three stages: message header parsing, data segment extraction, and verification. In the verification process, a cyclic redundancy check method is used. ,in The first Bytes, ensuring the integrity of data transmission. The data parsing module uses a state machine design pattern, which can effectively handle packet loss and disorder. The purpose of this step is to ensure the integrity and accuracy of data reception and provide a reliable data foundation for subsequent analysis.

[0050] The specific implementation of step S02 is to process the buoy latitude and longitude data based on the principle of empirical mode decomposition. First, the latitude and longitude data are converted into time series, and the time series data is preprocessed, including outlier processing and data smoothing. The data preprocessing uses the median filter method to remove outliers, and the filter window size is set to 5 data points. Achieve outlier removal. Then use cubic spline interpolation method to smooth the data, and set the interpolation node interval to 30 minutes. Then perform empirical mode decomposition on the preprocessed data, and the decomposition expression is , the time series is decomposed into multiple intrinsic mode functions through an iterative screening process. During the decomposition process, the iteration stop condition is set to a standard deviation threshold of 0.2, and the maximum number of iterations is 10. Finally, the obtained intrinsic mode functions are divided into two categories: stable components of buoy displacement and variable components of buoy displacement. Components with frequencies below 0.1 Hz are classified as stable components, and components above this frequency are classified as variable components. The purpose of this step is to separate the stable trend and fluctuation characteristics of the buoy displacement, providing a basis for subsequent displacement status judgment.

[0051] The multivariate decomposition operation in step S02 is specifically expressed as follows:

[0052] ;

[0053] Where, is the time series of buoy latitude and longitude data; is the stable component of buoy displacement; is the displacement variation component of the buoy; The number of decomposition layers ranges from 3 to 5.

[0054] The specific implementation of step S03 is to obtain and process environmental monitoring data. First, obtain environmental wind speed data, environmental wind direction data, and environmental flow direction data from the weather station, with a data sampling interval of 10 minutes. Perform quality control on the acquired environmental data, including data range check and time continuity check. The effective range of wind speed data is set to 0 to 60 meters per second, and the range of wind direction data is 0 to 360 degrees. Data out of range is corrected by interpolation method. Then, the environmental wind speed data is subjected to multi-scale analysis using wavelet decomposition method, and the decomposition expression is: , select Debao wavelet as the basis function, and set the decomposition level to 4. The wavelet transform coefficients are obtained by Calculate, where is the wavelet basis function. Reconstruction yields the stable and variable components of ambient wind speed. The reconstruction process utilizes a threshold denoising method, with the soft threshold function parameter set to three times the standard deviation. The goal of this step is to obtain high-quality ambient data and extract key wind speed features through signal processing.

[0055] The multivariate decomposition of wind speed in step S03 is specifically expressed as follows:

[0056] ;

[0057] Where, is the time series of ambient wind speed data; is the stable component of ambient wind speed; is the ambient wind speed variation component; The number of decomposition layers ranges from 3 to 5.

[0058] The specific implementation of step S04 is to establish a correlation model between buoy displacement and environmental factors. First, the least squares method is used to establish a preliminary relationship between the buoy displacement change component and the environmental wind speed change component. A weighted strategy is used in the fitting process, and the weight of recent data is set to a larger value. Then, the environmental flow direction data is introduced to construct the flow direction influence function. , the function is obtained by polynomial fitting, and the polynomial order is set to 3. Then the shift relationship function is established A genetic algorithm was used to optimize model parameters, with a population size of 100, 50 generations, a crossover probability of 0.8, and a mutation probability of 0.1. The algorithm's fitness function used the root mean square error (RMSE), and an iterative optimization process yielded the optimal weight coefficient combination. The goal of this step was to construct an accurate buoy displacement prediction model and accurately determine the buoy's displacement status.

[0059] The shift relationship function in step S04 is specifically expressed as follows:

[0060] ;

[0061] Where, is the float shift function; is the displacement variation component of the buoy; is the ambient wind speed variation component; is the flow direction influence function; is the weight coefficient, and its value range is 01; is the error term, and its value range is 0.010.1.

[0062] The buoy shift matrix is ​​specifically expressed as follows:

[0063] ;

[0064] Where, express time The shift coefficient in the direction.

[0065] The specific implementation of step S05 is to calculate the buoy stability matrix based on the buoy displacement matrix and determine the displacement state. First, the displacement coefficient is calculated by the sliding window method. The window length is set to 6 hours and the sliding step is 1 hour. For each time window, the displacement components in three orthogonal directions are calculated, and the weighted average method is used to obtain the displacement coefficient to construct the displacement matrix. Then the buoy stability matrix is ​​established, and the matrix elements are obtained by normalization. The normalization process uses the maximum and minimum method. Finally, the buoy displacement state is determined based on the eigenvalue of the stability matrix. The eigenvalue calculation adopts the power iteration method. ,The convergence threshold is set to 0.001.,The purpose of this step is to achieve a quantitative judgment of the buoy displacement state through ,matrix analysis method.

[0066] The specific implementation of step S06 is to perform time-frequency analysis on the buoy voltage data. First, the voltage data is reconstructed into a time series using the delayed coordinate method. The delay time is determined by the mutual information method, and the embedding dimension is determined by the false nearest neighbor method. Then, the reconstructed phase space is projected into two dimensions and a two-dimensional transformation is used. ,in is the original voltage time series. The projection method uses principal component analysis, and the number of transformation points is set to 1024. Then the spatial distribution characteristics of the voltage data are calculated ,in is the correction coefficient, and its value range is 0.1 to 0.3. The purpose of this step is to achieve early recognition of abnormal buoy voltage status through time-frequency analysis method.

[0067] The calculation of the two-dimensional transformation value in step S06 is specifically expressed as follows:

[0068] ;

[0069] Where, is the two-dimensional transformation value of the buoy voltage data; is the original voltage time series; Is an imaginary unit.

[0070] The specific implementation of step S07 involves calculating quantitative indicators of the voltage status. First, the rate of change of the voltage data in the time and amplitude dimensions is calculated using a central difference method with a difference step size equal to the sampling period. The spatial distribution characteristics of the rate of change are then calculated, including statistics such as mean, variance, and skewness. These characteristics are then combined to form a voltage fluctuation value, which is calculated based on the spatial gradient of the horizontal and vertical voltage values. The purpose of this step is to establish a quantitative assessment indicator of the voltage status and provide an objective basis for abnormality judgment.

[0071] The calculation of the fluctuation value in step S07 is specifically expressed as follows:

[0072] ;

[0073] Where, is the buoy voltage fluctuation value; is the voltage transverse value; is the longitudinal value of voltage; is the correction coefficient, and its value range is 0.1~0.3.

[0074] The specific implementation of step S08 is to analyze the time series characteristics of the buoy anchor light data. First, the theoretical sunrise and sunset times are calculated based on the astronomical algorithm, which takes into account the influence of geographical location and seasonal changes. Then, a theoretical model of the anchor light working cycle is constructed. ,in For a 24-hour cycle, is the seasonal adjustment coefficient, is the error term. The degree of match between the actual anchor light status and the theoretical model is then calculated using correlation analysis. The purpose of this step is to determine whether the buoy anchor light system is functioning properly by analyzing the anchor light's operating status.

[0075] The anchor light matching function in step S08 is specifically expressed as follows:

[0076] ;

[0077] Where, Matching function for buoy anchor light; For the day and night cycle, take 24 hours; is the seasonal adjustment coefficient; is the error term, and its value range is 0.05~0.15.

[0078] The specific implementation of step S09 is to monitor the buoy hatch and the water inflow status. First, the hatch data and the water inflow data are digitally processed to establish a safety judgment function. ,in is the door state function, is the water inflow state function, The weight coefficient is used. The status assessment results are updated in real time. The assessment process uses a sliding time window with a window length of 3 hours. The purpose of this step is to achieve timely detection and alarm of buoy intrusion events.

[0079] The safety determination function in step S09 is specifically expressed as follows:

[0080] ;

[0081] Where, is the safety judgment function; is the hatch state function; is the water inlet state function; is the weight coefficient, and its value range is 01; is the error term, and its value range is 0.010.1.

[0082] The specific implementation of steps S10 to S14 involves the comprehensive safety assessment of the buoy. First, the buoy safety assessment value is calculated based on the above indicators. ,in is the weight coefficient. The buoy displacement prediction is Calculations are performed and safety assessment is conducted based on the actual position of the buoy. The final marine safety assessment score is determined by The system categorizes risk levels based on the assessment scores: 100 points or higher is considered Class A, 40 to 100 points is considered Class B, and 0 to 40 points is considered Class C. Cluster analysis is used to determine the boundary values ​​based on the risk levels, and fuzzy rule reasoning is used to determine the buoy's risk level. Finally, appropriate action recommendations are automatically generated based on the risk level. The goal of this phase is to achieve quantitative assessment of the buoy's safety status and risk warning, providing decision support for buoy safety management.

[0083] The weighted calculation in step S13 is specifically expressed as follows:

[0084] ;

[0085] Where, is the safety assessment value of the buoy; It is the public safety value of the buoy; is the safety value of the buoy itself; It is the safety value of the buoy function; is the weight coefficient and satisfies ; is the systematic error, and its value range is 0.01~0.05.

[0086] These equations are constructed as follows:

[0087] 1. The multivariate decomposition operation adopts the principle of empirical mode decomposition, which can effectively separate the stable component and the variable component, facilitating subsequent analysis;

[0088] 2. The displacement relationship function takes into account multiple influences such as wind speed and flow direction, adopts the linear superposition principle, and introduces an error term to improve robustness;

[0089] 3. The two-dimensional transformation value calculation adopts the Fourier transform principle, which can better reflect the frequency domain characteristics of voltage data;

[0090] 4. The anchor light matching function is based on the periodic variation characteristics of trigonometric functions and can accurately describe the change pattern of day and night;

[0091] 5. The safety judgment function adopts a weighted summation form, taking into account the comprehensive impact of multiple safety factors;

[0092] 6. The calculation of the buoy safety assessment value adopts a linear weighted method, which can flexibly adjust the importance of each indicator.

[0093] The derivation and establishment process of each equation is explained in detail below.

[0094] 1. Multivariate decomposition equation of buoy latitude and longitude Derivation of:

[0095] First, extreme points are screened based on the original longitude and latitude sequence;

[0096] Secondly, perform cubic spline interpolation on the extreme points to obtain the upper envelope and lower envelope ;

[0097] Then, calculate the mean function ;

[0098] Then, separate the ;

[0099] Finally, the above process is iterated to obtain each component.

[0100] Parameter Description:

[0101] Obtained through iterative calculation, two conditions must be met:

[0102] The difference between the number of extreme points and the number of zero-crossing points does not exceed 1;

[0103] At any point, the mean of the mean envelope is approximately 0.

[0104] 2. Shift relation function Derivation of:

[0105] Step 1: Establish an initial model by fitting historical data using the least squares method;

[0106] Step 2: Introducing flow direction influence function Modify the model;

[0107] Step 3: Optimize weight coefficients through genetic algorithm .

[0108] Parameter acquisition method:

[0109] The experimental method is used to obtain the specific steps:

[0110] (1) Measure the buoy offset under different flow conditions;

[0111] (2) Establishing a mapping relationship between flow direction and offset;

[0112] (3) The flow direction influence function is obtained through polynomial fitting.

[0113] 3. Float shift matrix The build process:

[0114] Step 1: Calculate the displacement vector at adjacent moments;

[0115] Step 2: Decompose the displacement vector into three orthogonal directions;

[0116] Step 3: Calculate the shift coefficient in each direction using the sliding window method.

[0117] Matrix elements The calculation formula is:

[0118] ;

[0119] Where: is the window length; For the The weight of each sampling point; For the Sampling points in The displacement component in the direction.

[0120] 4. Voltage two-dimensional transformation value Derivation of:

[0121] The first step is to convert the original voltage sequence into the time-frequency domain. The second step is to introduce the complex exponential kernel function for two-dimensional transformation. The third step is to optimize the computational efficiency through fast Fourier transform.

[0122] Specific implementation steps:

[0123] (1) Rearrange the voltage data into a two-dimensional matrix;

[0124] (2) Perform Fourier transform on the row direction;

[0125] (3) Perform Fourier transform in the column direction;

[0126] (4) Extract the transformation coefficients.

[0127] 5. Buoy voltage fluctuation value Derivation of:

[0128] Step 1: Calculate the voltage spatial gradient:

[0129] ;

[0130] ;

[0131] Step 2: Introduce the correction factor Compensate for numerical calculation errors.

[0132] parameter Method for determining: Determine the optimal correction coefficient range through Monte Carlo simulation.

[0133] 6. Anchor light matching function Derivation of:

[0134] Step 1: Determine the sunrise and sunset times based on astronomical calculations; Step 2: Establish a benchmark periodic function; Step 3: Introduce a seasonal adjustment coefficient.

[0135] How to obtain the seasonal adjustment coefficient:

[0136] ;

[0137] ;

[0138] Where: For the accumulated days of the year; is the fitting coefficient.

[0139] 7. Security judgment function Derivation of:

[0140] Step 1: Construct the door status indication function:

[0141] ;

[0142] Step 2: Construct the water inlet state function:

[0143] ;

[0144] Step 3: Optimize weight coefficients through machine learning methods.

[0145] 8.Buoy safety assessment value Derivation of:

[0146] The first step is to determine the initial weights through the hierarchical analysis method; the second step is to modify the weights using the expert scoring method; the third step is to introduce systematic error terms to improve the robustness of the model.

[0147] Method for determining weight coefficient:

[0148] (1) Establish judgment matrix; (2) Calculate eigenvector; (3) Consistency test.

[0149] Specifically, the present invention's principle is as follows: Based on the principles of multi-source data fusion and multi-scale analysis, the technical solution organically integrates the buoy's displacement characteristics, state parameters, and environmental factors through the establishment of a mathematical model. For displacement analysis, the principle of empirical mode decomposition is employed. This method is highly adaptable and can handle nonlinear and non-stationary signals, effectively separating displacement characteristics at different scales. By analyzing the frequency characteristics of each scale component, it is possible to distinguish between periodic displacements caused by natural factors and sudden displacements under abnormal conditions. For environmental correlation analysis, a displacement relationship function is established based on fluid mechanics principles. This function accounts for the influence of environmental factors such as wind and current on buoy motion. Using a genetic algorithm to optimize weight coefficients, a precise correlation between environmental factors and buoy displacement is achieved. For condition monitoring, time-frequency analysis is used to process sensor data. By analyzing the signal's time and frequency domain characteristics, characteristic quantities reflecting the buoy's operating status are extracted. The system also establishes a fuzzy rule-based condition assessment model that can handle data uncertainty and improve the reliability of the assessment results. All these analysis results are weighted using the analytic hierarchy process to form the final safety assessment value. The innovations of this technical solution lie in: first, the precise description of buoy motion characteristics through multi-scale analysis; second, the establishment of a quantitative relationship between environmental factors and buoy status; and finally, the formation of a comprehensive safety assessment system. These mutually reinforcing technical innovations together form a logically rigorous technical solution that effectively solves the problem of identifying and assessing the safety status of buoys.

[0150] The following is a specific example 1 of the present invention. The specific methods of each step in this example 1 are described in detail as follows: A set of intelligent buoys with automatic safety monitoring functions were deployed in a certain sea area at 21 degrees 15 minutes north latitude and 114 degrees 32 minutes east longitude. The water depth in this area is approximately 150 meters, which is a nearshore environment near important shipping channels and fishing areas. The intelligent buoys are equipped with automatic meteorological observation and oceanographic hydrological monitoring functions, with a designed service life of three years. The buoys have a mass of 2000 kg, an anchor chain length of 180 meters, and a designed turning radius of 25 meters.

[0151] The buoy was deployed on January 10, 2024. This example selects the monitoring data of January 15, 2024 for analysis. First, the buoy message data is received through the satellite communication system, and the data reception quality index is The original message analysis results are shown in Table 1 below:

[0152]

[0153] The environmental monitoring data obtained during the same period are shown in Table 2:

[0154]

[0155] A multivariate decomposition of the longitude and latitude data was performed using the empirical mode decomposition method to obtain three intrinsic mode functions. The first component represents short-term fluctuations with a frequency of approximately 0.2 Hz; the second component represents medium-term changes with a frequency of approximately 0.05 Hz; and the third component represents long-term trends with a frequency below 0.01 Hz. The analysis results indicate that the buoy displacement is within the gyration radius and is considered normal.

[0156] After the environmental data is decomposed by wavelet, the stable component of wind speed is 8.5 meters per second, and the maximum amplitude of the variable component is 1.6 meters per second. The weight coefficient is obtained by calculating the shift relationship function , , The maximum eigenvalue of the shift matrix is ​​0.82, which is lower than the warning threshold of 0.9, indicating that the buoy is in a stable mooring state.

[0157] Voltage data analysis shows that the average voltage during the daytime (07:00-17:00) was 13.0 volts, and the average voltage during the nighttime (17:00-07:00) was 12.7 volts. The maximum voltage fluctuation was 0.15, below the abnormal threshold of 0.2, indicating that the power supply system is operating normally. The anchor light status matches the theoretical sunrise (06:58) and sunset (17:42) times well, with a deviation of less than 5 minutes.

[0158] The calculation results of the safety assessment indicators are shown in Table 3 below:

[0159]

[0160] The comparison between the present invention and the traditional buoy safety monitoring method is shown in Table 4 below:

[0161]

[0162] The specific application effect of this embodiment shows that this method can realize all-weather automatic monitoring of the safety status of the buoy, and has the following advantages over traditional methods:

[0163] 1. Utilizing multivariate decomposition and correlation analysis methods, the system improves the accuracy of abnormal state identification and reduces false positives and missed alerts. 2. A quantitative safety assessment system has been established, making safety management more objective and standardized. 3. Predictive early warnings are implemented, providing ample response time for safety measures. 4. The system exhibits excellent adaptability, automatically adjusting parameters based on environmental changes.

[0164] In practical applications, this method has been promoted and applied in multiple buoy monitoring stations in the South China Sea, achieved good results, and provided strong guarantees for the safe operation of buoys.

[0165] To better understand and implement the present invention, the following provides Example 2 of a specific application scenario of the present invention, namely, a buoy maritime safety automatic monitoring and assessment system:

[0166] 1.1. Buoy displacement monitoring method:

[0167] When the buoy's latitude and longitude data change, it is advisable to determine whether the buoy's position status is abnormal based on the buoy's speed and direction of movement, combined with measured wind, wave, and current data or corresponding forecast data. This mainly includes:

[0168] Slight positional changes of the moored buoy within the mooring turning radius are normal;

[0169] The buoy does not send back any positioning data, including the message data containing no positioning data, the original message cannot be parsed, and the independent positioning system does not send back any parsable positioning data.

[0170] If the buoy's longitude and latitude change significantly, calculate the displacement distance and direction between two adjacent times and make a judgment based on the measured (or predicted) wind speed, wind direction, and current direction at the same time. The method can be found in Table 5.

[0171] If the buoy's longitude and latitude change significantly, it is judged to be a false alarm, but if the movement occurs continuously and at a stable speed, it can be determined to be towing by a vessel.

[0172] Table 5 Buoy displacement determination table

[0173]

[0174] The displacement distance formula is as follows:

[0175] The distance the buoy moves from point A to point B , is the spherical distance between points A and B, that is, the minor arc of the great circle passing through points A and B. The longitude and latitude of points AB are A( , )、B( , ), the calculation formula is as follows:

[0176] ;

[0177] ;

[0178] Where: Indicates that the radius of the Earth is 6371km; It represents the central angle between points A and B; Indicates latitude; Indicates longitude.

[0179] 1.2. Buoy voltage safety monitoring method:

[0180] By analyzing the voltage data in the buoy message, the buoy voltage safety monitoring is carried out, including:

[0181] Under relatively consistent weather conditions, the buoy voltage begins to rise 2-3 hours after sunrise and begins to drop 2-3 hours after sunset. The voltage returned by the buoy status information should be higher than the minimum rated voltage of each buoy sensor.

[0182] The maximum voltage of the buoy battery should remain stable. If the maximum voltage decreases, it is necessary to determine whether it is caused by bad weather based on data such as wind speed, temperature, air pressure, relative humidity, and visibility.

[0183] If the voltage is normal for many days and the voltage returned by the buoy status information is lower than the minimum rated voltage of each buoy sensor, excluding bad weather, it can be determined that the power system is faulty;

[0184] After the voltage alarm, the alarm will be lifted the next time. If there is no voltage alarm for 24 consecutive hours, the buoy voltage can be determined to be normal. When monitoring the buoy voltage, the influence of the buoy's longitude and latitude, sunlight angle, season, weather, obstruction (ice and snow), etc. should be considered.

[0185] 1.3. Safety monitoring method of buoy anchor light:

[0186] By analyzing the anchor light data in the buoy message, the safety monitoring of the buoy anchor light is carried out, including:

[0187] The buoy anchor light should be light-sensitive, kept in the "off" state during the day and kept in the "on" state at night. The "on" and "off" switching process should be continuous and in accordance with physical laws, and should not occur multiple times a day;

[0188] There should be no significant change in the on and off times of the buoy anchor light on adjacent dates, and the working hours should be consistent with the seasonal characteristics of the area where the buoy is located.

[0189] 1.4. Buoy hatch safety monitoring method:

[0190] Door sensors should be installed at the entry and exit doors. Based on the door alarm information, buoy door safety monitoring should be carried out, including:

[0191] After receiving the door sensor alarm, continuously monitor the buoy working status for 3 hours. If the alarm is lifted or the system is working normally, it is a false alarm or the sensor is loose.

[0192] If the entire system fails within 3 hours of monitoring and is determined to be caused by the hatch being open and an outsider entering and damaging the buoy system, a joint judgment should be made based on the water ingress into the buoy compartment.

[0193] 1.5. Buoy tank water ingress monitoring method:

[0194] The tank water ingress sensor should be installed at the bottom of the buoy instrument. According to the tank water ingress alarm information, the buoy water ingress safety monitoring should be carried out, including:

[0195] After the water inflow sensor alarms, the buoy status and water inflow situation are analyzed by combining the buoy voltage data and hatch alarm information;

[0196] After the water inflow sensor alarms, the maximum wave height data at the corresponding time is used to analyze whether a ship collision has occurred.

[0197] 1.6. Buoy message status monitoring method:

[0198] By analyzing the buoy parsed message and original message status monitoring, it specifically includes:

[0199] If the buoy currently displays no data, it is advisable to check the original message to determine whether the buoy has no data to send back or has data but cannot be parsed;

[0200] In the original message record, by analyzing the internal code of the buoy, the communication method number, the receiving time and the message time, whether the current time message can be manually parsed and whether the latitude and longitude information can be manually read.

[0201] 2. Buoy maritime safety assessment:

[0202] 2.1 Buoy maritime safety assessment indicators:

[0203] 2.1.1 Indicators affecting public safety:

[0204] Factors affecting public safety mainly include factors that have been detected by security monitoring and the buoy has been displaced, may or has entered disputed waters, or may pose a threat to public safety in offshore facilities, offshore aquaculture, waterway safety, etc.

[0205] 2.1.2 Indicators affecting the safety of the buoy itself

[0206] Factors that affect the buoy's own safety mainly include voltage failure, hatch opening, water ingress into the buoy, anchor light failure, anchor dragging, and other factors that affect the buoy's own safety during maritime safety monitoring.

[0207] 2.1.3 Indicators affecting buoy functional safety

[0208] Factors that affect the functional safety of buoys mainly include factors discovered during maritime safety monitoring that affect the safety of buoy observation activities due to message analysis, data transmission, sensor failure, etc.

[0209] 2.1.4 Maritime Safety Assessment Index Classification

[0210] The classification of buoy maritime safety assessment indicators can be found in Table 6.

[0211] Table 6 Classification of buoy maritime safety assessment indicators

[0212]

[0213] 2.2 Calculation of buoy maritime safety assessment:

[0214] ;

[0215] Where: represents the buoy maritime safety assessment score, 、 、 Assign values ​​to the indicators of maritime safety assessment that correspond to situations affecting public safety, affecting the safety of the buoy itself, and affecting the functional safety of the buoy.

[0216] 2.3 Buoy safety status assessment:

[0217] Table 7 Safe disposal methods for buoys at sea

[0218]

[0219] 3. The buoy displacement prediction formula is as follows:

[0220] ;

[0221] Where: Indicates the speed of the buoy, which can be calculated by referring to the following formula; It represents the sum of all driving forces acting on the buoy; Indicates the mass of an object; Indicates exercise time.

[0222] The hydrodynamic mathematical model is based on the Euler field, and the Lagrangian viewpoint is used to describe the motion of particles. In the Euler field, for a two-dimensional plane problem, the velocity of any point in space can be expressed as:

[0223] ;

[0224] Using the Lagrangian viewpoint, the velocity of any particle can be expressed as:

[0225] ;

[0226] The trajectory of the particle can be obtained by the following integral:

[0227] ;

[0228] If every moment It is known that the motion trajectory of the particle can be calculated from the above formula through numerical integration.

[0229] The variables and explanations of the present invention are shown in Table 8:

[0230]

[0231] The above description is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for automatically monitoring buoy marine safety, characterized in that: The method comprises the following steps: receiving buoy message data, wherein the buoy message data includes buoy latitude and longitude data, buoy voltage data, buoy anchor light data, buoy hatch data, buoy cabin water inflow data, and buoy sensor data; performing multivariate decomposition operation on the buoy latitude and longitude data, specifically converting the data into a time series, removing anomalies through median filtering, smoothing through cubic spline interpolation, and iteratively decomposing the data into multiple intrinsic mode functions to obtain a buoy displacement stable component and a buoy displacement variation component; obtaining an ambient wind speed stable component and an ambient wind speed variation component through reconstruction, and establishing a displacement relationship function between the buoy displacement variation component and the ambient wind speed variation component, that is, using the least squares method to establish a preliminary relationship, polynomial fitting to construct a flow direction influence function, and genetic algorithm to optimize parameters; Constructing a buoy shift matrix based on the shift relationship function, calculating the shift coefficient using a sliding window method, calculating the displacement components in three orthogonal directions and performing normalization processing, and calculating the eigenvalue using a power iteration method; Calculate the buoy's public safety value, the buoy's own safety value, and the buoy's functional safety value. The step of calculating the buoy's public safety value is to use the eigenvalue decomposition method to extract the main motion direction of the shift matrix, and evaluate the stability of the displacement in combination with the buoy's stability matrix. The step of calculating the buoy's own safety value is to use the trend analysis method to evaluate the voltage change trend and the periodic characteristics of the anchor light matching function. The step of calculating the buoy's functional safety value is to use the spectrum analysis method to identify abnormal periods. Based on the output result of the safety judgment function, the decision tree method is used to comprehensively evaluate the buoy's own safety status. The buoy's public safety value, the buoy's own safety value, and the buoy's functional safety value are weighted and calculated to obtain the buoy's safety assessment value. The buoy risk level is determined according to the buoy safety assessment value.

2. A method for automatically monitoring buoy marine safety according to claim 1, characterized in that: The steps for processing the buoy message data are specifically to receive the original message data through the communication receiving module, and use the recursive descent algorithm to process the hierarchical data structure, including message header parsing, data segment extraction, checksum verification, and use the state machine design pattern to handle data packet loss and disorder. The signal strength threshold is set to 25 decibels and the signal-to-noise ratio threshold is set to 10 decibels.

3. A method for automatically monitoring buoy marine safety according to claim 2, characterized in that: In the step of performing a multivariate decomposition operation on the buoy longitude and latitude data, the iteration stop condition is set to a standard deviation threshold of 0.2 to obtain a buoy displacement stability component and a buoy displacement variation component.

4. A method for automatically monitoring buoy marine safety according to claim 3, characterized in that: In the step of establishing the shift relationship function, the population size is set to 100, the evolutionary generations are 50, the crossover probability is 0.8, and the mutation probability is 0.

1.

5. A method for automatically monitoring buoy marine safety according to claim 4, characterized in that: The steps of constructing the buoy shift matrix are as follows: calculating the shift coefficient by the sliding window method, with the window length set to 6 hours and the sliding step length to 1 hour; calculating the displacement components in three orthogonal directions; normalizing the data using the maximum and minimum method; calculating the eigenvalue by the power iteration method; and setting the convergence threshold to 0.

001.

6. A method for automatically monitoring buoy marine safety according to claim 5, characterized in that: The steps of calculating the public safety value of the buoy are to extract the main movement direction of the buoy displacement matrix by using the eigenvalue decomposition method, evaluate the displacement stability in combination with the buoy stability matrix, and evaluate the potential impact of the buoy on public safety by using the fuzzy comprehensive evaluation method.

7. A method for automatically monitoring buoy marine safety according to claim 6, characterized in that: The steps of calculating the buoy's own safety value are specifically to use a trend analysis method to evaluate the buoy voltage change trend, use a spectrum analysis method to identify the abnormal period of the buoy anchor light matching function, and evaluate the buoy hatch data and buoy cabin water inflow data based on a decision tree method.

8. A method for automatically monitoring buoy marine safety according to claim 7, characterized in that: The steps for calculating the functional safety value of the buoy are specifically to use data quality control methods to identify abnormal values ​​and missing values ​​of buoy sensor data, calculate the time continuity index and spatial consistency index of the data, and use hierarchical analysis method to determine the index weights.

9. A method for automatically monitoring buoy marine safety according to claim 8, characterized in that: The calculation steps of the buoy safety assessment value are as follows: using the Delphi method to determine the initial weights of various safety indicators, optimizing the weight coefficients through the hierarchical analysis method and performing consistency tests, and obtaining the final buoy safety assessment value by weighted summation.

10. A method for automatic monitoring of buoy marine safety according to claim 9, characterized in that: The step of determining the risk level of the buoy is specifically to use a cluster analysis method to determine the level boundary value, and to use fuzzy rule reasoning to judge the risk level of the buoy.

Images